19 May 2023 in IEEE Transactions on Neural Networks and Learning Systems
Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions, especially for cohorts with different lung diseases. The attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This article presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network (FANN) and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization, and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19, and pulmonary fibrosis.
27 October 2022 in Computers in Biology and Medicine
Various structures in human physiology follow a treelike morphology, which often expresses complexity at very fine scales. Examples of such structures are intrathoracic airways, retinal blood vessels, and hepatic blood vessels. Large collections of 2D and 3D images have been made available by medical imaging modalities such as magnetic resonance imaging (MRI), computed tomography (CT), Optical coherence tomography (OCT) and ultrasound in which the spatial arrangement can be observed. Segmentation of these structures in medical imaging is of great importance since the analysis of the structure provides insights into disease diagnosis, treatment planning, and prognosis. Manually labelling extensive data by radiologists is often time-consuming and error-prone. As a result, automated or semi-automated computational models have become a popular research field of medical imaging in the past two decades, and many have been developed to date. In this survey, we aim to provide a comprehensive review of currently publicly available datasets, segmentation algorithms, and evaluation metrics. In addition, current challenges and future research directions are discussed.
1 April 2025 in Nature Genetics
The spatial organization of cells in tissues underlies biological function, and recent advances in spatial profiling technologies have enhanced our ability to analyze such arrangements to study biological processes and disease progression. We propose MESA (multiomics and ecological spatial analysis), a framework drawing inspiration from ecological concepts to delineate functional and spatial shifts across tissue states. MESA introduces metrics to systematically quantify spatial diversity and identify hot spots, linking spatial patterns to phenotypic outcomes, including disease progression. Furthermore, MESA integrates spatial and single-cell multiomics data to facilitate an in-depth, molecular understanding of cellular neighborhoods and their spatial interactions within tissue microenvironments. Applying MESA to diverse datasets demonstrates additional insights it brings over prior methods, including newly identified spatial structures and key cell populations linked to disease states. Available as a Python package, MESA offers a versatile framework for quantitative decoding of tissue architectures in spatial omics across health and disease.
28 June 2023 in IEEE Journal of Biomedical and Health Informatics
Automated airway segmentation models often suffer from discontinuities in peripheral bronchioles, which limits their clinical applicability. Furthermore, data heterogeneity across different centres and pathological abnormalities pose significant challenges to achieving accurate and robust segmentation in distal small airways. Accurate segmentation of airway structures is essential for the diagnosis and prognosis of lung diseases. To address these issues, we propose a patch-scale adversarial-based refinement network that takes in preliminary segmentation and original CT images and outputs a refined mask of the airway structure. Our method is validated on three datasets, including healthy cases, pulmonary fibrosis, and COVID-19 cases, and quantitatively evaluated using seven metrics. Our method achieves more than a 15% increase in the detected length ratio and detected branch ratio compared to previously proposed models, demonstrating its promising performance. The visual results show that our refinement approach, guided by a patch-scale discriminator and centreline objective functions, effectively detects discontinuities and missing bronchioles. We also demonstrate the generalizability of our refinement pipeline on three previous models, significantly improving their segmentation completeness. Our method provides a robust and accurate airway segmentation tool that can help improve diagnosis and treatment planning for lung diseases.
9 September 2026 in Nature Biomedical Engineering
Advances in generative protein design using artificial intelligence (AI) have enabled the rapid development of binders against heterogeneous targets, including tumour-associated antigens. Despite extensive biochemical characterization, these novel protein binders have had limited evaluation in candidate therapeutics, including chimaeric antigen receptor (CAR) T cells. Here we synthesize generative protein design workflows to screen 1,758 newly designed protein binders targeting BCMA, CD19 and CD22 for efficacy in scalable protein-binding, T-cell activation and in vivo killing assays. We characterize three main challenges that hinder the utility of de novo protein binders as CARs, including tonic signalling, occluded epitope engagement and off-target activity. We develop computational and experimental heuristics to overcome these limitations, including screens of sequence variants of individual parental structures, that retain on-target CAR activation while mitigating liabilities. Together, our framework accelerates the development of AI-designed proteins for future preclinical therapeutic screening, helping enable a new generation of cellular therapies.
15 September 2025 in IEEE Open Journal of Engineering in Medicine and Biology
Deep learning-based Generative Models have the potential to convert low-resolution CT images into high-resolution counterparts without long acquisition times and increased radiation exposure in thin-slice CT imaging. However, procuring appropriate training data for these Super-Resolution (SR) models is challenging. Previous SR research has simulated thick-slice CT images from thin-slice CT images to create training pairs. However, these methods either rely on simplistic interpolation techniques that lack realism or on sinogram reconstruction, which requires the release of raw data and complex reconstruction algorithms. Thus, we introduce a simple yet realistic method to generate thick CT images from thin-slice CT images, facilitating the creation of training pairs for SR algorithms. The training pairs produced by our method closely resemble real data distributions (PSNR=49.74 vs. 40.66, p<0.05). A multivariate Cox regression analysis involving thick slice CT images with lung fibrosis revealed that only the radiomics features extracted using our method demonstrated a significant correlation with mortality (HR=1.19 and HR=1.14, p<0.005). This paper represents the first to identify and address the challenge of generating appropriate paired training data for Deep Learning-based CT SR models, which enhances the efficacy and applicability of SR models in real-world scenarios.